改进现有的RetinaNet的量化
Open
Nobody has claimed this yet.
enhancement
- Dominant language
- Python
- Stars
- 306
- Forks
- 96
- PR merge metrics
- No merged PRs in 30d
Description
背景
1.实现fully量化的RetinaNet
2.将量化检测模型和vision/detection进行合并
任务描述
1.现有RetinaNet受MegEngine版本限制仅仅量化了backbone部分，后续需要一个fully量化的RetinaNet
2.检测量化部分code有部分冗余，需要进行合并
目标
将quant retinanet统一合入 vision/detection
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by comparing the existing quantized RetinaNet implementation with the vision/detection code, focusing on the current backbone-only quantization and duplicated detection quantization code. Done means RetinaNet is fully quantized and the quantized implementation is unified under vision/detection without the noted redundancy.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100